one-on-ones
О программе
Этот навык Claude предлагает структурированное руководство для проведения эффективных индивидуальных встреч, включая схемы повестки, наборы вопросов и работу со сложными разговорами. Он предназначен для разработчиков на руководящих ролях, чтобы выстраивать доверие, развивать членов команды и проактивно решать проблемы. Используйте его при настройке новых 1:1 встреч, перезапуске неэффективных совещаний или подготовке к обсуждениям производительности и карьерного развития.
Быстрая установка
Claude Code
Рекомендуетсяnpx skills add guia-matthieu/clawfu-skills -a claude-code/plugin add https://github.com/guia-matthieu/clawfu-skillsgit clone https://github.com/guia-matthieu/clawfu-skills.git ~/.claude/skills/one-on-onesСкопируйте и вставьте эту команду в Claude Code для установки этого навыка
Документация
One-on-Ones
Design and run effective 1:1 meetings that build trust, develop people, and surface problems before they become crises.
When to Use This Skill
- New manager setting up 1:1s for the first time
- Resetting unproductive 1:1s that became status updates
- Onboarding a new direct report with structured first conversations
- Preparing for a difficult conversation (performance, conflict, change)
- Career development coaching in 1:1 context
- Scaling management as team grows
Methodology Foundation
| Aspect | Details |
|---|---|
| Sources | Andy Grove (High Output Management), Kim Scott (Radical Candor), Michael Lopp (Managing Humans) |
| Core Principle | The 1:1 is the direct report's meeting, not the manager's — their time to surface what matters to them |
| Key Ratio | Manager talks 10-30% of the time; listens 70-90% |
What Claude Does vs What You Decide
| Claude Does | You Decide |
|---|---|
| Designs 1:1 cadence and structure for your team size | Personal relationship-building approach |
| Generates conversation frameworks and question banks | Which questions fit each person |
| Creates agenda templates and running-notes docs | How to adapt for individual personalities |
| Prepares scripts for difficult conversations | Final wording and tone for sensitive topics |
| Suggests development discussion frameworks | Career advice based on your knowledge of the person |
Instructions
Step 1: Set Up the Mechanics
Cadence by maturity:
| Task-Relevant Maturity | Frequency | Duration |
|---|---|---|
| New or struggling | 2x/week | 30-45 min |
| Developing | Weekly | 30-45 min |
| Senior / independent | Bi-weekly | 45-60 min |
Rules: Same time each week. Rarely cancel. They own the agenda (shared doc, they add topics first). Private space for sensitive topics.
30-minute structure:
| Time | Activity |
|---|---|
| 0-5 min | Check-in: "How are you, really?" |
| 5-20 min | Their agenda items |
| 20-25 min | Your topics (feedback, context) |
| 25-30 min | Commitments and close |
Step 2: Master the Conversation
Opening — Understand where they're at: "What's on your mind this week?" / "How's your energy level?"
Middle (their agenda) — Coach, don't solve:
- "Tell me more about that."
- "What have you tried?"
- "What do you think you should do?"
- "How can I help?"
Resist the urge to fix immediately. Ask → Listen → Ask more → Let them reach conclusions.
Middle (your topics) — Keep secondary. Feedback, context, observations.
Closing — Capture commitments: "What are you committing to? What am I committing to?" Document and review next time.
Step 3: Handle Different Conversation Types
Career Development (monthly/quarterly):
- "Where do you want to be in 2-3 years?"
- "What skills do you want to develop?"
- "What would make this the best job you've ever had?"
Feedback:
- Context → 2. Specific observation → 3. Impact → 4. Their perspective → 5. What should change
Performance concern:
- State the pattern with specific examples
- Ask: "Help me understand — what's happening?"
- Explain the impact
- Agree on path forward with clear expectations and timeline
- Document
Validation checkpoint: After a performance conversation, check in at the next 1:1. If no improvement after 2-3 follow-ups, escalate to formal process.
Trust-building (new relationship):
- "Tell me about your path to here."
- "How do you like to receive feedback?"
- "What do you need from me to do your best work?"
Step 4: Troubleshoot Common Problems
| Problem | Likely Cause | Fix |
|---|---|---|
| "Everything is fine" every week | Lack of trust or wrong questions | Wait in silence longer; share your own challenges first; ask "What would you change if you could?" |
| Turns into status update | Habit, no agenda ownership | "I can read status — what do you need from me?"; use shared doc for status, meeting for discussion |
| Same complaints, no action | Venting without ownership | "We've discussed this for weeks. Are you ready to address it?" |
| Surface-level only | Trust not established yet | Walk-and-talks, share about yourself, be patient |
| Too busy to hold 1:1s | Too many reports or not delegating | 1:1s are core management work, not optional — restructure |
Examples
Example: Onboarding a New Report
Week 1 (60 min): Getting to know each other — their story, working preferences, how they like feedback, your context and priorities.
Weeks 2-4 (30 min, 2x/week): Frequent check-ins — "What's surprising? What's confusing? What do you need?"
Week 4+: Transition to weekly cadence with shared running doc. Add development topics monthly.
90-day check-in: "How's it going overall? What's working? What's not? What do you want to focus on next quarter?"
Example: Resetting Stale 1:1s
The reset conversation: "I've noticed our 1:1s have become mostly status updates. I want to use this time for things you can't get elsewhere — challenges, development, feedback. What would make these more valuable for you?"
Then: implement shared agenda doc, change opening from "What's your update?" to "What's on your mind?", add 10 minutes for development each week, experiment with format (walks, coffee).
See QUESTIONS.md for a complete question bank organized by category (opening, work, development, relationship, closing).
Skill Boundaries
What This Skill Does Well
- Designing 1:1 systems and cadence for different team sizes
- Generating conversation frameworks and question banks
- Preparing scripts for difficult management conversations
- Diagnosing and fixing unproductive 1:1 patterns
What This Skill Cannot Do
- Replace real human judgment about individual personalities
- Handle legally sensitive HR situations (consult HR/legal)
- Know your team members — you provide the context
- Substitute for building genuine relationships over time
References
- Grove, Andy. High Output Management — 1:1 fundamentals
- Scott, Kim. Radical Candor — Caring personally + challenging directly
- Lopp, Michael. Managing Humans — Practical 1:1 advice
- Horowitz, Ben. The Hard Thing About Hard Things — Difficult conversations
Related Skills
- high-output-management — Grove's full management system
- radical-candor — Feedback framework for 1:1s
GitHub репозиторий
Frequently asked questions
What is the one-on-ones skill?
one-on-ones is a Claude Skill by guia-matthieu. Skills package instructions and resources that Claude loads on demand, so Claude can perform one-on-ones-related tasks without extra prompting.
How do I install one-on-ones?
Use the install commands on this page: add one-on-ones to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does one-on-ones belong to?
one-on-ones is in the Meta category, tagged design.
Is one-on-ones free to use?
Yes. one-on-ones is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
Похожие навыки
Этот навык предоставляет проверенную в продакшене настройку для Content Collections — TypeScript-ориентированного инструмента, который преобразует файлы Markdown/MDX в типобезопасные коллекции данных с валидацией Zod. Используйте его при создании блогов, сайтов документации или контентных приложений на Vite + React для обеспечения типобезопасности и автоматической проверки содержимого. Он охватывает всё: от настройки плагина Vite и компиляции MDX до оптимизации развертывания и валидации схем.
Этот навык позволяет разработчикам создавать приложения на платформе прогнозных рынков Polymarket, включая интеграцию с API для торговли и получения рыночных данных. Он также обеспечивает потоковую передачу данных в реальном времени через WebSocket для отслеживания текущих сделок и рыночной активности. Используйте его для реализации торговых стратегий или создания инструментов, обрабатывающих обновления рынка в реальном времени.
Этот навык помогает разработчикам создавать плагины OpenCode, которые подключаются к более чем 25 типам событий, таким как команды, файлы и операции LSP. Он предоставляет структуру плагина, спецификации API событий и шаблоны реализации для модулей на JavaScript/TypeScript. Используйте его, когда вам нужно перехватывать, отслеживать или расширять жизненный цикл ассистента OpenCode AI с помощью пользовательской событийно-ориентированной логики.
SGLang — это высокопроизводительный фреймворк для обслуживания больших языковых моделей (LLM), специализирующийся на быстрой структурированной генерации JSON, regex и рабочих процессов агентов с использованием кэширования префиксов RadixAttention. Он обеспечивает значительно более высокую скорость вывода, особенно для задач с повторяющимися префиксами, что делает его идеальным для сложных структурированных результатов и многократных диалогов. Выбирайте SGLang вместо альтернатив, таких как vLLM, когда вам требуется ограниченное декодирование или вы создаете приложения с интенсивным совместным использованием префиксов.
